# \[ImageNet\]A question about Data Augmentation

**URL:** <https://discuss.pytorch.org/t/imagenet-a-question-about-data-augmentation/67074>\
**Category:** Uncategorized\
**Created:** [January 19, 2020, 4:42am UTC](https://discuss.pytorch.org/t/imagenet-a-question-about-data-augmentation/67074 "2020-01-19T04:42:28Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![cclover](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/cclover/32/18341_2.png) [@cclover](https://discuss.pytorch.org/u/cclover)\
**Post date:** [January 19, 2020, 4:42am UTC](https://discuss.pytorch.org/t/imagenet-a-question-about-data-augmentation/67074/1 "2020-01-19T04:42:28Z")

</div>

The first form of data augmentation consists of generating image translations and horizontal reflections. We do this by extracting random **224 × 224** patches (and their horizontal reflections) from the  
256×256 images and training our network on these extracted patches4. This increases the size of our  
training set by a factor of 2048, though the resulting training examples are, of course, highly interdependent. Without this scheme, our network suffers from substantial overfitting, which would have  
forced us to use much smaller networks. At test time, the network makes a prediction by extracting  
five 224 × 224 patches (the four corner patches and the center patch) as well as their horizontal  
reflections (hence ten patches in all), and averaging the predictions made by the network’s softmax  
layer on the ten patches.

I do not know why make the input images are **224x224x3**  
**The passage is from "ImageNet Classification with Deep Convolutional**  
**Neural Networks "of 4.1**

---

<div class="post-metadata">

**Author:** ![ptrblck](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ptrblck/32/1823_2.png) [@ptrblck](https://discuss.pytorch.org/u/ptrblck)\
**Post date:** [January 20, 2020, 1:15am UTC](https://discuss.pytorch.org/t/imagenet-a-question-about-data-augmentation/67074/2 "2020-01-20T01:15:01Z")

</div>

My best guess is that this shape is somehow the “standard” for ImageNet-related models.  
AlexNet used it and a lot of models adapted the shape.

The models were originally written in the sense that the input shape had to be constant, which would also explain a specific shape which “just works”.  
Today you would most likely find model implementations with adaptive pooling layers, which allow different input shapes.